Skip to main content
AI Accessibility Benchmark

Beta

Test results

Pick a model to see how accessible its components are, with the accessibility skill off and on.

Gemini 4 Argon

Skill version 2.3

Results for 22 components, each generated 3 times.Each acceptance criterion is counted once per component if it fails in any generation.
MeasureSkill offSkill on
Failed acceptance criteria220
of which WCAG150
of which Best practice70
Total cost (US dollars)$4.84$10.85

Tooltip

Results, totals across all generations

Failed acceptance criteria

Each acceptance criterion is counted once per component if it fails in any generation.

Skill off
2 fails
WCAG
2 fails
Best practice
0 fails
Skill on
0 fails
WCAG
0 fails
Best practice
0 fails

Efficiency, average per generation

Input tokens include cache reads.

Cost in USD

Input tokens

Skill off
8,188 tokens
Skill on
58,821 tokens

Output tokens

Skill off
3,738 tokens
Skill on
7,264 tokens

Turns

Skill off
4 turns
Skill on
6 turns

Time

Skill off
73 seconds
Skill on
100 seconds

Cost

Skill off
$0.05
Skill on
$0.13

Generated components

Prompt given to the model
Build a page with one button labelled "Shipping details" in a single self-contained HTML file (inline CSS and JS, no build step, no external libraries). Hovering over or focusing the button shows a small pop-up box next to it containing the text "Orders ship within 2 business days." The pop-up is not shown when the page first loads. Output the complete code in one HTML code block.
Skill off
Skill on

Acceptance criteria

Show

Showing 11 of 11 criteria

Semantic markup5 criteria

  • The tooltip content's role of tooltip is included in the accessibility tree.WCAG 4.1.2Automated
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • The tooltip content's accessible name is included in the accessibility tree.WCAG 4.1.2Automated
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • When the tooltip content is visible, it is in the accessibility tree.WCAG 1.3.1Automated
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • The tooltip content is programmatically associated with its trigger using aria-describedby.WCAG 1.3.1Automated
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • The tooltip content does not contain interactive elements (for example, links, buttons, or form fields).Best practiceAutomated
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass

Keyboard3 criteria

  • The tooltip content is visible when the interactive control has focus.WCAG 2.1.1Browser
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • The tooltip content is visible when the interactive control is hovered over.WCAG 1.4.13Browser
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • The tooltip content is dismissible by pressing the Escape key or clicking outside of it.WCAG 1.4.13Browser
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass

Visual design2 criteria

  • The tooltip content remains visible when the mouse cursor moves from the trigger to the tooltip content itself.WCAG 1.4.13Browser
    Skill off

    1/3 failed

    • Generation 1: Pass
    • Generation 2: Fail
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
  • The tooltip content remains visible until the trigger loses hover or focus, the user dismisses it, or the information it contains becomes invalid. It does not disappear automatically after a fixed time while the trigger still has hover or focus.WCAG 1.4.13Browser
    Skill off

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass

Adaptive UI1 criterion

  • The tooltip content can be viewed at smaller screen widths (320px) without loss of content or functionality, and without requiring horizontal scrolling.WCAG 1.4.10Browser
    Skill off

    2/3 failed

    • Generation 1: Fail
    • Generation 2: Fail
    • Generation 3: Pass
    Skill on

    3/3 passed

    • Generation 1: Pass
    • Generation 2: Pass
    • Generation 3: Pass

Back to top